Reliable Prediction Errors for Deep Neural Networks Using Test-Time Dropout

TL;DR

This paper introduces a computationally efficient method combining Test-Time Dropout and Conformal Prediction to generate reliable prediction errors for deep neural networks, validated on bioactivity datasets and virtual screening tasks.

Contribution

The paper presents a novel framework that uses Test-Time Dropout with Conformal Prediction to produce valid and efficient prediction intervals for neural networks in drug discovery.

Findings

Dropout Conformal Predictors are valid across multiple datasets.

Prediction intervals are narrower than those from Random Forest models.

The method achieves comparable virtual screening performance to RF-based methods.

Abstract

While the use of deep learning in drug discovery is gaining increasing attention, the lack of methods to compute reliable errors in prediction for Neural Networks prevents their application to guide decision making in domains where identifying unreliable predictions is essential, e.g. precision medicine. Here, we present a framework to compute reliable errors in prediction for Neural Networks using Test-Time Dropout and Conformal Prediction. Specifically, the algorithm consists of training a single Neural Network using dropout, and then applying it N times to both the validation and test sets, also employing dropout in this step. Therefore, for each instance in the validation and test sets an ensemble of predictions were generated. The residuals and absolute errors in prediction for the validation set were then used to compute prediction errors for test set instances using Conformal Prediction. We show using 24 bioactivity data sets from ChEMBL 23 that dropout Conformal Predictors are valid (i.e., the fraction of instances whose true value lies within the predicted interval strongly correlates with the confidence level) and efficient, as the predicted confidence intervals span a narrower set of values than those computed with Conformal Predictors generated using Random Forest (RF) models. Lastly, we show in retrospective virtual screening experiments that dropout and RF-based Conformal Predictors lead to comparable retrieval rates of active compounds. Overall, we propose a computationally efficient framework (as only N extra forward passes are required in addition to training a single network) to harness Test-Time Dropout and the Conformal Prediction framework, and to thereby generate reliable prediction errors for deep Neural Networks.